Graph Engineering
18 records · 4 notes · records tagged with this as a related axis are included.
The different things one word, "graph," can point to
These days "graph" means at least three things: control graphs that set the order in which an agent runs, knowledge graphs that store facts and relationships, and computation graphs through which a model's calculations run. Because they share a name, discussions often get tangled, so they get an axis of their own. Here, the first thing noted is which kind of graph is meant.
A strand that reorganizes agent long-term memory, which had relied on a single graph structure, into a triple structure of timeline, graph and documents, with provenance tracking and citation locks. In the authors' own r
Using Airbnb listing research as the example, the steps for implementing graph engineering end to end are as follows. Before running the whole graph, test a single pipeline end to end on one area only, Gangnam-gu, and se
On the same task, depending on whether you use one coding agent or split the work up, performance can rise by more than 80% or drop by 70%. Anthropic's Research feature improved by more than 90% with parallel splitting a
The core skill of AI engineering has moved from prompt (2022) → context (2024) → harness (late 2025) → loop → graph engineering, and each stage was born from the limits of the one before it. As models got smarter, prompt
A strand that does not take LLM-extracted graph edges at face value but recalibrates edge weights after the fact through counterfactual intervention — tackling, before the retrieval stage, the edge-reliability problem lo
Opens a parametric knowledge-graph strand that, unlike the GraphRAG lineage, which queries the graph at retrieval time, compiles the graph into model weights in advance — while at the same time pinning down that this str
Graph engineering is confusing because three things get lumped under one word: control graphs (making agents reliable through SOPs), knowledge graphs (retrieval based on entity relationships — an unrelated concept) and g
A strand that redefines the knowledge graph of agentic systems from a "flat store of extracted triples" into an object of governance that records who owns a fact, why it was adopted and how it should be used. In the auth
Brings into the mainstream the self-criticism that evaluations centered on retrieval metrics have overstated the benefits of graph techniques
Showed that agentic search narrows the gap between the two approaches, updating the 2024 GraphRAG debate
The turning point into a phase of testing with benchmarks when graphs actually help — the methodological forerunner of the 2026 skepticism
A commercial agent long-term memory product adopted graph representations as a core extension — graph engineering spreading beyond RAG into the memory layer
The original GraphRAG authors acknowledged the cost problem themselves and turned toward deferred graph construction
The open-source camp's leading lightweight alternative to the costly indexing of Microsoft GraphRAG
Community complaints that the official implementation was heavyweight surfaced as a hackable, ultra-light reimplementation
A case of Chinese Big Tech industrializing the GraphRAG lineage for professional domains (finance, healthcare)
Brought a sprawl of variants under one taxonomy, formalizing graph-based RAG as a research field of its own
The point at which a research technique spread as a widely replicable implementation
The multi-hop retrieval branch of the GraphRAG lineage
Handles global summarization queries that local retrieval cannot answer
An early case of a graph DB vendor adopting GraphRAG as a product category — the point at which an academic term entered the commercial stack
A lineage of structured indexes beyond vector similarity search